Training in progress, step 600
Browse files- config.json +1 -1
- last-checkpoint/config.json +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +2 -2
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +13 -421
- last-checkpoint/training_args.bin +2 -2
- pytorch_model.bin +2 -2
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -39,7 +39,7 @@
|
|
| 39 |
"pad_token_id": 1,
|
| 40 |
"position_embedding_type": "absolute",
|
| 41 |
"torch_dtype": "float32",
|
| 42 |
-
"transformers_version": "4.
|
| 43 |
"type_vocab_size": 1,
|
| 44 |
"use_cache": true,
|
| 45 |
"vocab_size": 250002
|
|
|
|
| 39 |
"pad_token_id": 1,
|
| 40 |
"position_embedding_type": "absolute",
|
| 41 |
"torch_dtype": "float32",
|
| 42 |
+
"transformers_version": "4.31.0",
|
| 43 |
"type_vocab_size": 1,
|
| 44 |
"use_cache": true,
|
| 45 |
"vocab_size": 250002
|
last-checkpoint/config.json
CHANGED
|
@@ -39,7 +39,7 @@
|
|
| 39 |
"pad_token_id": 1,
|
| 40 |
"position_embedding_type": "absolute",
|
| 41 |
"torch_dtype": "float32",
|
| 42 |
-
"transformers_version": "4.
|
| 43 |
"type_vocab_size": 1,
|
| 44 |
"use_cache": true,
|
| 45 |
"vocab_size": 250002
|
|
|
|
| 39 |
"pad_token_id": 1,
|
| 40 |
"position_embedding_type": "absolute",
|
| 41 |
"torch_dtype": "float32",
|
| 42 |
+
"transformers_version": "4.31.0",
|
| 43 |
"type_vocab_size": 1,
|
| 44 |
"use_cache": true,
|
| 45 |
"vocab_size": 250002
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2117841669
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aafda980146253cd7b82b0dd2e2a1211ce96ed9fccbf804597a542c6abfab59e
|
| 3 |
size 2117841669
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:925941313b310518092ca4c0ce765c6ed1e75d6a07a200cdf61def1fa48fdef8
|
| 3 |
+
size 2268273785
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a45a08059f2351fc7b31a0c40f1b65158be9ff667b5b2468faf63f546d65222b
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90b1e78b64b76d121ce0a17312e4bc1a4adeafa3fb2ee51db16618bc84d92166
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,440 +1,32 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 0.04,
|
| 12 |
-
"eval_accuracy": 0.7687216869069928,
|
| 13 |
-
"eval_f1": 0.7665424923390772,
|
| 14 |
-
"eval_loss": 0.9364227652549744,
|
| 15 |
-
"eval_runtime": 684.6631,
|
| 16 |
-
"eval_samples_per_second": 197.963,
|
| 17 |
-
"eval_steps_per_second": 0.774,
|
| 18 |
-
"step": 400
|
| 19 |
-
},
|
| 20 |
{
|
| 21 |
"epoch": 0.05,
|
| 22 |
-
"learning_rate": 9.
|
| 23 |
-
"loss": 1.
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"eval_accuracy": 0.
|
| 29 |
-
"eval_f1": 0.
|
| 30 |
-
"eval_loss":
|
| 31 |
-
"eval_runtime":
|
| 32 |
-
"eval_samples_per_second":
|
| 33 |
-
"eval_steps_per_second": 0.
|
| 34 |
-
"step":
|
| 35 |
-
},
|
| 36 |
-
{
|
| 37 |
-
"epoch": 0.1,
|
| 38 |
-
"learning_rate": 9.989538300104932e-06,
|
| 39 |
-
"loss": 0.8696,
|
| 40 |
-
"step": 1000
|
| 41 |
-
},
|
| 42 |
-
{
|
| 43 |
-
"epoch": 0.13,
|
| 44 |
-
"eval_accuracy": 0.846795732562086,
|
| 45 |
-
"eval_f1": 0.8476031571339556,
|
| 46 |
-
"eval_loss": 0.7674374580383301,
|
| 47 |
-
"eval_runtime": 684.9072,
|
| 48 |
-
"eval_samples_per_second": 197.892,
|
| 49 |
-
"eval_steps_per_second": 0.774,
|
| 50 |
-
"step": 1200
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 0.16,
|
| 54 |
-
"learning_rate": 9.98429171038825e-06,
|
| 55 |
-
"loss": 0.8001,
|
| 56 |
-
"step": 1500
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.17,
|
| 60 |
-
"eval_accuracy": 0.8562469565730644,
|
| 61 |
-
"eval_f1": 0.8555885462291756,
|
| 62 |
-
"eval_loss": 0.7412897348403931,
|
| 63 |
-
"eval_runtime": 685.4288,
|
| 64 |
-
"eval_samples_per_second": 197.742,
|
| 65 |
-
"eval_steps_per_second": 0.773,
|
| 66 |
-
"step": 1600
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 0.21,
|
| 70 |
-
"learning_rate": 9.97906610703043e-06,
|
| 71 |
-
"loss": 0.7653,
|
| 72 |
-
"step": 2000
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.21,
|
| 76 |
-
"eval_accuracy": 0.8584087119479408,
|
| 77 |
-
"eval_f1": 0.8589656756888883,
|
| 78 |
-
"eval_loss": 0.7346311807632446,
|
| 79 |
-
"eval_runtime": 1253.8639,
|
| 80 |
-
"eval_samples_per_second": 108.096,
|
| 81 |
-
"eval_steps_per_second": 0.423,
|
| 82 |
-
"step": 2000
|
| 83 |
-
},
|
| 84 |
-
{
|
| 85 |
-
"epoch": 0.25,
|
| 86 |
-
"eval_accuracy": 0.8606590033791262,
|
| 87 |
-
"eval_f1": 0.8613764873641668,
|
| 88 |
-
"eval_loss": 0.7210016846656799,
|
| 89 |
-
"eval_runtime": 749.1336,
|
| 90 |
-
"eval_samples_per_second": 180.926,
|
| 91 |
-
"eval_steps_per_second": 0.707,
|
| 92 |
-
"step": 2400
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 0.26,
|
| 96 |
-
"learning_rate": 9.973840503672613e-06,
|
| 97 |
-
"loss": 0.7517,
|
| 98 |
-
"step": 2500
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 0.29,
|
| 102 |
-
"eval_accuracy": 0.8668491493160589,
|
| 103 |
-
"eval_f1": 0.8662439909072627,
|
| 104 |
-
"eval_loss": 0.7115087509155273,
|
| 105 |
-
"eval_runtime": 748.5848,
|
| 106 |
-
"eval_samples_per_second": 181.059,
|
| 107 |
-
"eval_steps_per_second": 0.708,
|
| 108 |
-
"step": 2800
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 0.31,
|
| 112 |
-
"learning_rate": 9.968604407135362e-06,
|
| 113 |
-
"loss": 0.7386,
|
| 114 |
-
"step": 3000
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.34,
|
| 118 |
-
"eval_accuracy": 0.8676090837993773,
|
| 119 |
-
"eval_f1": 0.8684186652379281,
|
| 120 |
-
"eval_loss": 0.7080894708633423,
|
| 121 |
-
"eval_runtime": 748.8743,
|
| 122 |
-
"eval_samples_per_second": 180.989,
|
| 123 |
-
"eval_steps_per_second": 0.708,
|
| 124 |
-
"step": 3200
|
| 125 |
-
},
|
| 126 |
-
{
|
| 127 |
-
"epoch": 0.37,
|
| 128 |
-
"learning_rate": 9.963389296956978e-06,
|
| 129 |
-
"loss": 0.7238,
|
| 130 |
-
"step": 3500
|
| 131 |
-
},
|
| 132 |
-
{
|
| 133 |
-
"epoch": 0.38,
|
| 134 |
-
"eval_accuracy": 0.8690256607003202,
|
| 135 |
-
"eval_f1": 0.8697884276426098,
|
| 136 |
-
"eval_loss": 0.7015646696090698,
|
| 137 |
-
"eval_runtime": 666.7136,
|
| 138 |
-
"eval_samples_per_second": 203.293,
|
| 139 |
-
"eval_steps_per_second": 0.795,
|
| 140 |
-
"step": 3600
|
| 141 |
-
},
|
| 142 |
-
{
|
| 143 |
-
"epoch": 0.42,
|
| 144 |
-
"learning_rate": 9.958153200419727e-06,
|
| 145 |
-
"loss": 0.7216,
|
| 146 |
-
"step": 4000
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 0.42,
|
| 150 |
-
"eval_accuracy": 0.8712390621080435,
|
| 151 |
-
"eval_f1": 0.8724240607774923,
|
| 152 |
-
"eval_loss": 0.6999966502189636,
|
| 153 |
-
"eval_runtime": 666.1677,
|
| 154 |
-
"eval_samples_per_second": 203.459,
|
| 155 |
-
"eval_steps_per_second": 0.796,
|
| 156 |
-
"step": 4000
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.46,
|
| 160 |
-
"eval_accuracy": 0.87027992149803,
|
| 161 |
-
"eval_f1": 0.8704618561200863,
|
| 162 |
-
"eval_loss": 0.6968262195587158,
|
| 163 |
-
"eval_runtime": 666.1311,
|
| 164 |
-
"eval_samples_per_second": 203.47,
|
| 165 |
-
"eval_steps_per_second": 0.796,
|
| 166 |
-
"step": 4400
|
| 167 |
-
},
|
| 168 |
-
{
|
| 169 |
-
"epoch": 0.47,
|
| 170 |
-
"learning_rate": 9.952906610703044e-06,
|
| 171 |
-
"loss": 0.7123,
|
| 172 |
-
"step": 4500
|
| 173 |
-
},
|
| 174 |
-
{
|
| 175 |
-
"epoch": 0.5,
|
| 176 |
-
"eval_accuracy": 0.8710250999719635,
|
| 177 |
-
"eval_f1": 0.8710228151932407,
|
| 178 |
-
"eval_loss": 0.6919674277305603,
|
| 179 |
-
"eval_runtime": 666.6562,
|
| 180 |
-
"eval_samples_per_second": 203.31,
|
| 181 |
-
"eval_steps_per_second": 0.795,
|
| 182 |
-
"step": 4800
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 0.52,
|
| 186 |
-
"learning_rate": 9.94766002098636e-06,
|
| 187 |
-
"loss": 0.708,
|
| 188 |
-
"step": 5000
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 0.55,
|
| 192 |
-
"eval_accuracy": 0.8743452020835485,
|
| 193 |
-
"eval_f1": 0.8736511770234788,
|
| 194 |
-
"eval_loss": 0.6875823736190796,
|
| 195 |
-
"eval_runtime": 666.8888,
|
| 196 |
-
"eval_samples_per_second": 203.239,
|
| 197 |
-
"eval_steps_per_second": 0.795,
|
| 198 |
-
"step": 5200
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"epoch": 0.58,
|
| 202 |
-
"learning_rate": 9.94242392444911e-06,
|
| 203 |
-
"loss": 0.705,
|
| 204 |
-
"step": 5500
|
| 205 |
-
},
|
| 206 |
-
{
|
| 207 |
-
"epoch": 0.59,
|
| 208 |
-
"eval_accuracy": 0.8718293024834364,
|
| 209 |
-
"eval_f1": 0.8721073032565451,
|
| 210 |
-
"eval_loss": 0.6912590861320496,
|
| 211 |
-
"eval_runtime": 666.9048,
|
| 212 |
-
"eval_samples_per_second": 203.234,
|
| 213 |
-
"eval_steps_per_second": 0.795,
|
| 214 |
-
"step": 5600
|
| 215 |
-
},
|
| 216 |
-
{
|
| 217 |
-
"epoch": 0.63,
|
| 218 |
-
"learning_rate": 9.937208814270725e-06,
|
| 219 |
-
"loss": 0.6986,
|
| 220 |
-
"step": 6000
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 0.63,
|
| 224 |
-
"eval_accuracy": 0.8746108102524753,
|
| 225 |
-
"eval_f1": 0.8755518143887745,
|
| 226 |
-
"eval_loss": 0.6850203275680542,
|
| 227 |
-
"eval_runtime": 670.2388,
|
| 228 |
-
"eval_samples_per_second": 202.223,
|
| 229 |
-
"eval_steps_per_second": 0.791,
|
| 230 |
-
"step": 6000
|
| 231 |
-
},
|
| 232 |
-
{
|
| 233 |
-
"epoch": 0.67,
|
| 234 |
-
"eval_accuracy": 0.8748395283979401,
|
| 235 |
-
"eval_f1": 0.8750168188156892,
|
| 236 |
-
"eval_loss": 0.6849112510681152,
|
| 237 |
-
"eval_runtime": 670.7573,
|
| 238 |
-
"eval_samples_per_second": 202.067,
|
| 239 |
-
"eval_steps_per_second": 0.79,
|
| 240 |
-
"step": 6400
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"epoch": 0.68,
|
| 244 |
-
"learning_rate": 9.93196222455404e-06,
|
| 245 |
-
"loss": 0.6986,
|
| 246 |
-
"step": 6500
|
| 247 |
-
},
|
| 248 |
-
{
|
| 249 |
-
"epoch": 0.71,
|
| 250 |
-
"eval_accuracy": 0.8763077513317299,
|
| 251 |
-
"eval_f1": 0.8766362923981238,
|
| 252 |
-
"eval_loss": 0.6798161864280701,
|
| 253 |
-
"eval_runtime": 669.9612,
|
| 254 |
-
"eval_samples_per_second": 202.307,
|
| 255 |
-
"eval_steps_per_second": 0.791,
|
| 256 |
-
"step": 6800
|
| 257 |
-
},
|
| 258 |
-
{
|
| 259 |
-
"epoch": 0.73,
|
| 260 |
-
"learning_rate": 9.926715634837356e-06,
|
| 261 |
-
"loss": 0.6948,
|
| 262 |
-
"step": 7000
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 0.76,
|
| 266 |
-
"eval_accuracy": 0.8761897032566512,
|
| 267 |
-
"eval_f1": 0.8771094350236266,
|
| 268 |
-
"eval_loss": 0.6797441840171814,
|
| 269 |
-
"eval_runtime": 670.6385,
|
| 270 |
-
"eval_samples_per_second": 202.103,
|
| 271 |
-
"eval_steps_per_second": 0.79,
|
| 272 |
-
"step": 7200
|
| 273 |
-
},
|
| 274 |
-
{
|
| 275 |
-
"epoch": 0.79,
|
| 276 |
-
"learning_rate": 9.921469045120673e-06,
|
| 277 |
-
"loss": 0.694,
|
| 278 |
-
"step": 7500
|
| 279 |
-
},
|
| 280 |
-
{
|
| 281 |
-
"epoch": 0.8,
|
| 282 |
-
"eval_accuracy": 0.8757765349938763,
|
| 283 |
-
"eval_f1": 0.875946128594897,
|
| 284 |
-
"eval_loss": 0.6784085631370544,
|
| 285 |
-
"eval_runtime": 670.4256,
|
| 286 |
-
"eval_samples_per_second": 202.167,
|
| 287 |
-
"eval_steps_per_second": 0.791,
|
| 288 |
-
"step": 7600
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 0.84,
|
| 292 |
-
"learning_rate": 9.916232948583422e-06,
|
| 293 |
-
"loss": 0.6907,
|
| 294 |
-
"step": 8000
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"epoch": 0.84,
|
| 298 |
-
"eval_accuracy": 0.8782776785846036,
|
| 299 |
-
"eval_f1": 0.8778960944609727,
|
| 300 |
-
"eval_loss": 0.6746197938919067,
|
| 301 |
-
"eval_runtime": 670.9876,
|
| 302 |
-
"eval_samples_per_second": 201.998,
|
| 303 |
-
"eval_steps_per_second": 0.79,
|
| 304 |
-
"step": 8000
|
| 305 |
-
},
|
| 306 |
-
{
|
| 307 |
-
"epoch": 0.88,
|
| 308 |
-
"eval_accuracy": 0.8770529298056634,
|
| 309 |
-
"eval_f1": 0.8765354326008715,
|
| 310 |
-
"eval_loss": 0.6747441291809082,
|
| 311 |
-
"eval_runtime": 1255.3569,
|
| 312 |
-
"eval_samples_per_second": 107.968,
|
| 313 |
-
"eval_steps_per_second": 0.422,
|
| 314 |
-
"step": 8400
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 0.89,
|
| 318 |
-
"learning_rate": 9.911007345225604e-06,
|
| 319 |
-
"loss": 0.6879,
|
| 320 |
-
"step": 8500
|
| 321 |
-
},
|
| 322 |
-
{
|
| 323 |
-
"epoch": 0.94,
|
| 324 |
-
"learning_rate": 9.905781741867787e-06,
|
| 325 |
-
"loss": 0.6875,
|
| 326 |
-
"step": 9000
|
| 327 |
-
},
|
| 328 |
-
{
|
| 329 |
-
"epoch": 0.94,
|
| 330 |
-
"eval_accuracy": 0.8780932284672933,
|
| 331 |
-
"eval_f1": 0.879247713093542,
|
| 332 |
-
"eval_loss": 0.6763164401054382,
|
| 333 |
-
"eval_runtime": 687.9898,
|
| 334 |
-
"eval_samples_per_second": 197.006,
|
| 335 |
-
"eval_steps_per_second": 0.77,
|
| 336 |
-
"step": 9000
|
| 337 |
-
},
|
| 338 |
-
{
|
| 339 |
-
"epoch": 1.0,
|
| 340 |
-
"learning_rate": 9.900545645330536e-06,
|
| 341 |
-
"loss": 0.686,
|
| 342 |
-
"step": 9500
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 1.01,
|
| 346 |
-
"eval_accuracy": 0.8796352314480071,
|
| 347 |
-
"eval_f1": 0.8798913903465643,
|
| 348 |
-
"eval_loss": 0.6714671850204468,
|
| 349 |
-
"eval_runtime": 688.5552,
|
| 350 |
-
"eval_samples_per_second": 196.844,
|
| 351 |
-
"eval_steps_per_second": 0.77,
|
| 352 |
-
"step": 9600
|
| 353 |
-
},
|
| 354 |
-
{
|
| 355 |
-
"epoch": 1.05,
|
| 356 |
-
"learning_rate": 9.895309548793285e-06,
|
| 357 |
-
"loss": 0.6828,
|
| 358 |
-
"step": 10000
|
| 359 |
-
},
|
| 360 |
-
{
|
| 361 |
-
"epoch": 1.07,
|
| 362 |
-
"eval_accuracy": 0.8783293246174505,
|
| 363 |
-
"eval_f1": 0.8770525463818627,
|
| 364 |
-
"eval_loss": 0.6699363589286804,
|
| 365 |
-
"eval_runtime": 734.0798,
|
| 366 |
-
"eval_samples_per_second": 184.637,
|
| 367 |
-
"eval_steps_per_second": 0.722,
|
| 368 |
-
"step": 10200
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 1.1,
|
| 372 |
-
"learning_rate": 9.890073452256035e-06,
|
| 373 |
-
"loss": 0.679,
|
| 374 |
-
"step": 10500
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 1.13,
|
| 378 |
-
"eval_accuracy": 0.8791187711195384,
|
| 379 |
-
"eval_f1": 0.8798211781418543,
|
| 380 |
-
"eval_loss": 0.6693193912506104,
|
| 381 |
-
"eval_runtime": 733.9523,
|
| 382 |
-
"eval_samples_per_second": 184.669,
|
| 383 |
-
"eval_steps_per_second": 0.722,
|
| 384 |
-
"step": 10800
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 1.15,
|
| 388 |
-
"learning_rate": 9.884837355718784e-06,
|
| 389 |
-
"loss": 0.679,
|
| 390 |
-
"step": 11000
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 1.18,
|
| 394 |
-
"eval_accuracy": 0.8803435198984787,
|
| 395 |
-
"eval_f1": 0.8801011265002094,
|
| 396 |
-
"eval_loss": 0.6679297685623169,
|
| 397 |
-
"eval_runtime": 684.5882,
|
| 398 |
-
"eval_samples_per_second": 197.985,
|
| 399 |
-
"eval_steps_per_second": 0.774,
|
| 400 |
-
"step": 11200
|
| 401 |
-
},
|
| 402 |
-
{
|
| 403 |
-
"epoch": 1.21,
|
| 404 |
-
"learning_rate": 9.8795907660021e-06,
|
| 405 |
-
"loss": 0.678,
|
| 406 |
-
"step": 11500
|
| 407 |
-
},
|
| 408 |
-
{
|
| 409 |
-
"epoch": 1.22,
|
| 410 |
-
"eval_accuracy": 0.8807862001800233,
|
| 411 |
-
"eval_f1": 0.8812929844052909,
|
| 412 |
-
"eval_loss": 0.6662477254867554,
|
| 413 |
-
"eval_runtime": 684.0407,
|
| 414 |
-
"eval_samples_per_second": 198.143,
|
| 415 |
-
"eval_steps_per_second": 0.775,
|
| 416 |
-
"step": 11600
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 1.26,
|
| 420 |
-
"learning_rate": 9.874354669464849e-06,
|
| 421 |
-
"loss": 0.6767,
|
| 422 |
-
"step": 12000
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 1.26,
|
| 426 |
-
"eval_accuracy": 0.8794138913072349,
|
| 427 |
-
"eval_f1": 0.8799114820136512,
|
| 428 |
-
"eval_loss": 0.6668325662612915,
|
| 429 |
-
"eval_runtime": 685.344,
|
| 430 |
-
"eval_samples_per_second": 197.766,
|
| 431 |
-
"eval_steps_per_second": 0.773,
|
| 432 |
-
"step": 12000
|
| 433 |
}
|
| 434 |
],
|
| 435 |
"max_steps": 953000,
|
| 436 |
"num_train_epochs": 100,
|
| 437 |
-
"total_flos":
|
| 438 |
"trial_name": null,
|
| 439 |
"trial_params": null
|
| 440 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.06295907660020986,
|
| 5 |
+
"global_step": 600,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 9.99476390346275e-06,
|
| 13 |
+
"loss": 1.6498,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"eval_accuracy": 0.430292611666101,
|
| 19 |
+
"eval_f1": 0.31503797170432934,
|
| 20 |
+
"eval_loss": 1.56297767162323,
|
| 21 |
+
"eval_runtime": 713.0904,
|
| 22 |
+
"eval_samples_per_second": 190.071,
|
| 23 |
+
"eval_steps_per_second": 0.743,
|
| 24 |
+
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"max_steps": 953000,
|
| 28 |
"num_train_epochs": 100,
|
| 29 |
+
"total_flos": 2.544857570206464e+16,
|
| 30 |
"trial_name": null,
|
| 31 |
"trial_params": null
|
| 32 |
}
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14dd9d3e983872605882053c5baf561625d8c8afd79b7a7ea8eef6f99645bedb
|
| 3 |
+
size 4027
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:925941313b310518092ca4c0ce765c6ed1e75d6a07a200cdf61def1fa48fdef8
|
| 3 |
+
size 2268273785
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14dd9d3e983872605882053c5baf561625d8c8afd79b7a7ea8eef6f99645bedb
|
| 3 |
+
size 4027
|